Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mq
    -0.07
    4
    -0.07
    Almost
    -0.06
    _OPTION
    -0.06
    费用
    -0.06
     Almost
    -0.06
    .badlogic
    -0.06
    Cum
    -0.06
    .Delay
    -0.06
    lng
    -0.06
    POSITIVE LOGITS
     discrepancies
    0.07
     Paula
    0.06
     alternate
    0.06
     hect
    0.06
     đoán
    0.06
    匹
    0.06
     buluş
    0.06
     dě
    0.06
     `(
    0.06
    홈
    0.06
    Act Density 0.082%

    No Known Activations